News for hackers. Stuff that matters.

A comment on Qwen2.5: A Party of Foundation Models. Parent comment

Re:Qwen2.5: A Party of Foundation Models by yourMadness on Wednesday September 18, 2024 @04:58PM (#41585398)
14B with Q4_K_M quantization is about 9 GB.

Remarkable that it is at all comparable to Sonnet 3.5

[ Parent | on HN ]
Re:Qwen2.5: A Party of Foundation Models by diggan on Wednesday September 18, 2024 @05:36PM (#41585842)
Comparable, I guess. But the result is a lot worse compared to Sonnet for sure. Parts of the example code doesn't make much sense. Meanwhile Sonnet seems to have the latest API of Bevy considered, and mostly makes sense.
[ Parent | on HN ]